experiment
Design rigorous experiments for a research paper: hypothesis formulation, variable identification, methodology selection, and success criteria. Produces a structured experiment plan with reproducibility in mind.
What this skill does
# Experiment Design
Help the researcher design rigorous experiments or computational studies. Good experiments are hypothesis-driven, reproducible, and have clear success criteria before they are run.
## Step 1: Read Context
Read `.papermill/state.md` (Read tool) for:
- **Thesis**: The claim the experiments should support or test.
- **Existing experiments**: Any previously registered experiments.
- **Format and tools**: What languages/tools are in the repo (R, Python, C++, etc.).
If `.papermill/state.md` does not exist, ask the user what claim the experiments should test. Experiment design can proceed without the state file — suggest running `/papermill:init` afterward to register experiments persistently.
Scan the repository for existing code (Glob tool) in `research/`, `code/`, `scripts/`, `experiments/`, or `analysis/` directories.
## Step 2: Identify What Needs Testing
Ask the user: "What specific claim or aspect of your thesis do these experiments need to support?"
Different contribution types need different experimental approaches:
| Contribution | Experimental approach |
|-------------|----------------------|
| Theorem/proof | Numerical validation of theoretical predictions |
| Algorithm | Runtime/accuracy benchmarks against baselines |
| Statistical method | Monte Carlo simulations with known ground truth |
| Empirical finding | Controlled experiments with statistical tests |
| Framework/model | Case studies demonstrating applicability |
## Step 3: Design the Experiment
For each experiment, specify:
### Hypothesis
State the expected outcome in falsifiable terms. "We expect X to be Y under conditions Z" -- not "we want to show our method works."
### Variables
- **Independent variables**: What you manipulate (parameters, dataset size, algorithm choice).
- **Dependent variables**: What you measure (accuracy, runtime, error rate).
- **Control variables**: What you hold constant (hardware, random seeds, data preprocessing).
### Methodology
- Data generation or collection procedure
- Algorithm/method configuration
- Number of replications or samples
- Statistical tests to apply (t-test, bootstrap CI, etc.)
- Baseline comparisons
### Success Criteria
Define **before running** what constitutes support for the hypothesis. This prevents post-hoc rationalization.
### Reproducibility
- Random seed strategy
- Hardware/software environment
- Data availability
- Script that runs the full experiment end-to-end
## Step 4: Address Common Pitfalls
Check for and warn about:
- **Cherry-picking**: Are you testing one configuration or sweeping parameters fairly?
- **Multiple comparisons**: If running many tests, apply correction (Bonferroni, FDR).
- **Overfitting to test data**: Is there a held-out validation set?
- **Computational budget**: Is this feasible given available hardware and time?
- **Missing baselines**: Every method needs comparison to something. Even "no method" is a baseline.
## Step 5: Register the Experiment
If `.papermill/state.md` exists, update it (Edit tool) by adding to the `experiments` list. If it does not exist, skip registration and suggest running `/papermill:init` to persist the experiment.
```yaml
experiments:
- name: "descriptive-name"
type: "simulation | benchmark | case-study | ablation"
hypothesis: "Expected outcome in one sentence"
status: "planned | running | completed | failed"
script: "path/to/script.R"
last_run: null
```
Append a timestamped note documenting the experiment design.
## Step 6: Suggest Next Steps
Based on the experiment type, suggest the most relevant next step:
- If this is a Monte Carlo study → "Use `/papermill:simulation` for detailed simulation design — it covers sample sizes, convergence diagnostics, and result presentation."
- If the experiment involves proving a theoretical prediction → "Consider `/papermill:proof` to verify the theory before running experiments."
- If results will need statistical analysis → "Implement the script, run it, then use `/papermill:review` once the results are written up."
- For all experiments → "Start with a small pilot run to debug before the full experiment."
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.